● Support NGS experiments to quantify and characterize on/off-targets of gene modifications by performing data wrangling and analysis, using open-source methods (e.g., CALITAS, CHANGE-Seq, CRISPResso2, GUIDE-Seq, Cas-OFFinder) and custom scripts.

● Query, retrieve, and integrate data from public genomics databases, to characterize alignments between CRISPR target sequences and guide RNAs.

● Compare concordance and sensitivity of five CRISPR off-target detection methods.

● Spearhead implementation of reproducible, robust bioinformatics data practices

● Established department-first machine learning pipeline to study effects of biomarker operations on quality of cancer immunotherapy assays.

● Generated over ten percent annual operation cost reduction via analysis of vendor performance over twenty clinical sites.

● Upgraded data operations for six data streams, including flow cytometry, biomarker operations, and oncology data warehouses.

● Monitored and solved sample data quality issues for two clinical trial arms.

● Collaborated with AI engineers to create an ETL pipeline for multi-modal survival prediction and patient stratification, by using Python machine learning and R/Bioconductor to integrate gene panel and RNA-Seq data.

● Tested and refined a textual entity and geolocation matching pipeline for clinical trial site management, resulting in over 90% accuracy.

● Designed ETL data pipeline for integration of real-world EHRs into deep learning module, using Python, SQL, and Apache Spark.

● Organized and managed close coordination of gRED Artificial Intelligence, data management, and DevOps functions, to bring clinical machine learning from prototype to production.

● Established an integrated genetic and curated literature workflow to predict incidence and prevalence rates of over sixty rare, genetic disorders, with R statistical and visualization packages (ggplot2) and MATLAB.

● Upgraded and tested RNA-Seq data pipeline (STAR2, SAMtools, Bioconductor) to discern disease contribution of rare variants to neural disease.

● Spearheaded development of three relational databases derived from Hail HPC population genomics platform, in collaboration with software engineer.

● Co-authored manuscript submitted to peer-reviewed publication, on prediction of disease severity in metachromatic leukodystrophy.

● Mentored research associates in developing bioinformatic skills, specifically in multiple sequence alignment and standard molecular biological protocols (restriction enzyme digestion, gel electrophoresis, spectrophotometry).

● Identified over forty putative conserved vertebrate phosphodiesterase proteins, by using multiple sequence alignment and genomic evidence.